© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14461
    Prev
    Next
    INDEX
    Explanations

    Japanese given‑name kanji

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tas
    -21.88
    tal
    -17.00
    ��
    -17.00
     Grape
    -16.88
    unal
    -16.75
     grape
    -16.63
    Downloads
    -16.50
    ган
    -16.25
    vfs
    -16.13
    unity
    -16.00
    POSITIVE LOGITS
    设
    14.94
    孰
    14.06
    辅
    13.13
    设置
    12.88
    彻
    12.69
    audi
    12.44
    achi
    12.31
    adol
    12.25
    _AUT
    12.19
    _hi
    12.06
    Activations Density 0.019%

    No Known Activations